Florian Wilhelm
where else to find them
website:https://florianwilhelm.info/
github:FlorianWilhelm
bluesky:florianwilhelm.bsky.social
linkedin:florianwilhelm
speakerdeck:florianwilhelm
what they talk about
all 6 in the filters
where they keep going back
- code.talks2 editions2022–2023
- PyData Berlin2 editions2017–2018
all 6 in the filters
on a stage with
- Arnab Duttaonce
- Markus Schüleronce
who talks about the same things
- Tereza Iofciu15 talks
- Ines Montani17 talks
- Valerio Maggio14 talks
- Alexander CS Hendorf25 talks
- Vincent D Warmerdam22 talks
- Laura Summers9 talks
| title | conference | date |
|---|---|---|
| Unlocking the Power of Integer Programming: Beginner’s Guide to Conference Scheduling | code.talks 2023 | 2023-09-14 |
Integer (0/1) linear programming is used to assign roughly 120 talks into 7 rooms over 3 days by encoding hard constraints (one assignment per talk… | ||
| Forget about AI and do mathematical modeling instead! | code.talks 2022 | 2022-09-15 |
Argues that much AI is a hype bubble and gives concrete counterexamples: over 2,000 COVID projects deliver little value, recommender teams spend millions yet… | ||
| Honey, I shrunk the target variable! Common pitfalls when transforming the targe... | PyCon DE & PyData Berlin 2022 | 2022-04-11 |
Claims that transforming the target (log) changes what the model actually minimizes and shows the math: minimizing RMSE on log targets yields the median when… | ||
| Are You Sure about That?! Uncertainty Quantification in AI | Big Data Conference Europe 2019 | 2019-11-26 |
Evaluates Gaussian processes, deep ensembles, Monte Carlo dropout and quantile regression on a noisy 0–10 regression with σ=0.5 using two‑layer NNs (20 units)… | ||
| How mobile.de brings Data Science to Production... | PyData Berlin 2018 | 2018-07-06 |
Personalization at mobile.de uses Hadoop/HDFS, PySpark and TensorFlow to build production systems: a logistic‑regression buyer‑intent model reaches 70%… | ||
| “Which car fits my life?” - mobile.de’s approach to recommendations | PyData Berlin 2017 | 2017-06-23 |
mobile.de runs a hybrid recommender that combines collaborative matrix factorization with content vectors to handle a rapidly changing 1.6 million-item… | ||
| the idea behind Automatic Relevance Determination and Bayesian Interpolation | PyData Amsterdam 2016 | 2016-03-12 |
Explains the actual claim that Automatic Relevance Determination recovers sparse weights by placing independent precisions on each coefficient and selecting… | ||
| "It's about time to take your medication!" or how to write a friendly reminder bot ;-) | EuroPython 2015 | 2015-07-20 |
A working chatbot that reminds someone to take long‑acting insulin and waits for confirmation, resends up to three times and then gives up is built and shown… | ||
| nothing matches | ||